The bunch of comparable demos for Multimodal VLMs (excels in OCR, cinematography understanding, spatial reasoning, etc.) now up on the Hub 🤗 — max recent till Jun'25.
The demo for Camel-Doc-OCR-062825 (exp) is optimized for document retrieval and direct Markdown (.md) generation from images and PDFs. Additional demos include OCRFlux-3B (document OCR), VilaSR (spatial reasoning with visual drawing), and ShotVL (cinematic language understanding). 🐪
The community GPU grant was given by Hugging Face — special thanks to them. This space supports the following tasks: (image inference, video inference) with result markdown canvas and object detection/localization. 🤗🚀
. . . To know more about it, visit the model card of the respective model. !!
The demo for DREX-062225-exp (Document Retrieval and Extraction eXpert ~ experimental) / typhoon-ocr-3b (a bilingual document parsing model built specifically for real-world documents) / VIREX-062225-exp (Video Information Retrieval and Extraction eXpert ~ experimental) / olmOCR-7B-0225-preview (the document parsing model based on Qwen2VL). 🤗
Updated the docscopeOCR-7B-050425-exp with the DREX-062225-exp, with improved preciseness in table structure and line spacing in the markdown used on the document page. And though this is still an experimental one, it's expected to perform well in the defined DREX use cases [ Document Retrieval and Extraction eXpert – experimental ocr ]. 💻
The demo for smoldocling / nanonets ocr / typhoon ocr / monkey ocr explores the document OCR capabilities of various newly released multimodal VLMs in a single space. And if you're experiencing or demoing long document image OCR, kindly use the Smoldocling 256M preview [ Smoldocling is back in demo here. ] 🤗.
The demo for the MonkeyOCR Recognition model, which adopts a Structure-Recognition-Relation (SRR) triplet paradigm & Nanonets-OCR-s a powerful, state-of-the-art image-to-markdown OCR model that goes far beyond traditional text extraction and other experimental document OCR models, is combined into a single space.
OpenAI, Google, Hugging Face, and Anthropic have released guides and courses on building agents, prompting techniques, scaling AI use cases, and more. Below are 10+ minimalistic guides and courses that may help you in your progress. 📖
Just made a demo for Cosmos-Reason1, a physical AI model that understands physical common sense and generates appropriate embodied decisions in natural language through long chain-of-thought reasoning. Also added video understanding support to it. 🤗🚀
Got access to Google's all-new Gemini Diffusion a state-of-the-art text diffusion model. It delivers the performance of Gemini 2.0 Flash-Lite at 5x the speed, generating over 1000 tokens in a fraction of a second and producing impressive results. Below are some initial outputs generated using the model. ♊🔥
The more optimized explicit content filters with lightweight 𝙜𝙪𝙖𝙧𝙙 models trained based on siglip2 patch16 512 and vit patch16 224 for illustration and explicit content classification for content moderation in social media, forums, and parental controls for safer browsing environments. this version fixes the issues in the previous release, which lacked sufficient resources. 🚀
hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥
as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!
in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.
Models for detecting images generated by diffusion models (Flux.1, SDXL, ..) are trained or fine-tuned using image classification models for content moderation. These models use datasets available on the Hub. For identifying AI-generated images or moderating visual content, the recommended model is OpenSDI-Flux.1-SigLIP2.😺🧨
Dropping some image classification models for content moderation and classifiers trained with datasets available on the Hub. All are fine-tuned on the siglip2 backbone, (competitions AIOrNot, Imagenette, and Driver-Drowsiness). Models and datasets are listed below:
🔗Collection : [The previous collection of models is also listed in the same collection, so you can find more models focused on image classification tasks.]
Dropping some image classification models for content moderation, balancers, and classifiers trained on synthetic datasets—along with others based on datasets available on the Hub. Also loaded a few low-rank datasets for realistic gender portrait classification and document-type classifiers, all fine-tuned on the SigLIP-2 Patch-16 224 backbone. Models and datasets are listed below:
Well, here’s the updated version with the 20,000+ entry sampled dataset for Watermark Filter Content Moderation models incl. [Food25, Weather, Watermark, Marathi/Hindi Sign Language Detection], post-trained from the base models: sigLip2 patch16 224 — now with mixed aspect ratios for better performance and reduced misclassification. 🔥
